Job Scout- Three models now vote on every job listing. The same batch of about 150 listings goes to Claude, GPT and Muse, and each model gives every job one verdict: strong (worth applying to this week), moderate (worth a second look) or skip, with a one-line reason. Each model's reply is filed under its name, so every job ends up with up to three votes, and a model asked again replaces only its own earlier votes. A job the person hasn't marked yet is sorted by the votes: a majority wins, and a true split (three different verdicts) lands on moderate, because that's exactly what a split is — worth a second look.
- Every job card shows its votes as chips, one per model, with the model's reason on hover. (GIF) shows the same job cards as Claude, then GPT, then Muse cast their votes.
- The vote register is a table of every voted job with each model's verdict and reason side by side, the combined result, and the person's own mark. Splits come first, since those are the jobs where a human call matters most. (screenshot)
- The person still decides. A job they marked themselves keeps their mark whatever the votes say; the votes are still recorded, so the register shows where the models disagreed with them.
- What the first real run showed. Across one day's 144 listings, the three models agreed on 100, split two to one on 43, and all differed on one. The disagreements clustered: one model consistently rated technical, customer-facing architect roles higher than the other two did. The register also exposed two problems in Job Scout itself, not in the models' judgment: for some employers the trimmed description sent to the models was nothing but company boilerplate, so they were judging job titles; and some listings tagged remote named only an office city.
Revised 2026-09-25: now says what the models vote on — job listings to consider applying to.
